Jul 2026· The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences· 0 citations· 5 references
TL;DR
Three Gaussian splatting methods as implemented in the Postshot commercial software were tested and show that MILo shows very promising results in terms of detail reconstruction, while standard Gaussian splatting excels in visualisation but is still plagued by a high rate of noise especially when converted into a geometric point cloud form.
Abstract
Abstract. In recent years, Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as advanced methods for photogrammetry-based 3D reconstruction. Since its introduction in 2020, NeRF has gained significant attention due to its capability to generate high-fidelity reconstructions from multi-view imagery. More recently, 3D Gaussian Splatting (3DGS), introduced in 2023, has proposed an alternative explicit scene representation based on a collection of anisotropic Gaussian primitives optimized directly in 3D space. This representation allows efficient rendering and scalable modelling of complex scenes while maintaining high visual quality. This paper analyses the performance of different 3DGS methods when dealing with complex geometry and less-cooperative surfaces compared to standard SfM IM procedures. Included in the comparison is also the Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction (MILo), a novel meshing method using Gaussian splats. Three Gaussian splatting methods as implemented in the Postshot commercial software were also tested. Our experiments show that MILo shows very promising results in terms of detail reconstruction, while standard Gaussian splatting excels in visualisation but is still plagued by a high rate of noise especially when converted into a geometric point cloud form.
This work proposes a hybrid reconstruction pipeline, leveraging the strengths and benefits of each technique, which exploits the accurate geometry of photogrammetry in well-textured regions and the GS capabilities to improve completeness and visual aspect in areas featuring non-collaborative surfaces.
Fabio Remondino, E. M. Farella, Gianluca Bertolasi et al.· The International Archives o...· 0 citations
This work investigates the potential of Mesh-In-the-Loop Gaussian Splatting (MILo), a recent extension of 3D Gaussian Splatting (3DGS) that integrates differentiable mesh extraction directly within the optimization process, enabling bidirectional consistency between volumetric and surface representations.
D. Billi, Chaimaa Delasse, Arnadi Murtiyoso et al.· The International Archives o...· 0 citations
3D Gaussian Splatting (3DGS) has recently attracted considerable attention as an efficient representation for high-quality novel-view synthesis. However, 3DGS typically relies on a large number of Gaussian primitives, making perceptually informed level-of-detail control essential for balancing visual quality and rendering efficiency. In this paper, we present an object-space analysis framework of contrast sensitivity for 3D Gaussian representations. By exploiting the analytical Fourier transform of Gaussian primitives and the projection–slice theorem, we estimate the spatial frequency response of projected Gaussians without explicit rasterization. This enables direct perceptual assessment of Gaussian primitives in object space under given viewing conditions. As an application of this analysis, we integrate the proposed perceptual assessment into a hierarchical 3DGS representation and realize a foveated rendering scheme that selects appropriate Gaussian levels at runtime using simple comparisons. Experimental results on real-world scenes demonstrate that the proposed method preserves visual quality while reducing rendering cost compared to full-quality rendering.
Naoto Yoshii, Suguru Saito, Masataka Sawayama et al.· International Conference on...· 0 citations
Neural radiance fields (NeRF) and 3D Gaussian Splatting (3DGS) are popular techniques to reconstruct and render photorealistic images. However, the prerequisite of running Structure-from-Motion (SfM) to get camera poses limits their completeness. Although previous methods can reconstruct a few unposed images, they are not applicable when images are unordered or densely captured. In this work, we propose a method to train 3DGS from unposed images. Our method leverages a pre-trained 3D geometric foundation model as the neural scene representation. Since the accuracy of the predicted pointmaps does not suffice for accurate image registration and high-fidelity image rendering, we propose to mitigate the issue by initializing and fine-tuning the pre-trained model from a seed image. The images are then progressively registered and added to the training buffer, which is used to train the model further. We also propose to refine the camera poses and pointmaps by minimizing a point-to-camera ray consistency loss across multiple views. When evaluated on diverse challenging datasets, our method outperforms state-of-the-art pose-free NeRF/3DGS methods in terms of both camera pose
Yu Chen, Rolandos Alexandros Potamias, Evangelos Ververas et al.· Neural Information Processin...· 0 citations
This work proposes an Iterative Spatial Decomposition framework that bridges dense geometric priors from Multi-View Stereo (MVS) with Gaussian Splatting and introduces Hierarchical Geometric Prior Sampling (HGPS), which substantially reduce redundancy in MVS point clouds while preserving critical details, thereby providing a more robust geometric foundation for reconstruction.
Zonghua Yu, Junhuai Li, Huaijun Wang et al.· ACM Transactions on Multimed...· 0 citations
A semantic-guided 3D Gaussian splatting (3DGS) framework tailored to sparse-view industrial reconstruction was introduced, enabling robust reconstruction from limited viewpoints and offers a practical geometric foundation for automated inspection and remote equipment monitoring.
Boyang Li, Tian-Han Gao, Zuan Gu et al.· Visual Computing for Industr...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
